athena.data.datasets.tts.speech_synthesis_test

audio dataset

Module Contents

Classes

SpeechSynthesisTestDatasetBuilder

SpeechSynthesisDatasetBuilder

class athena.data.datasets.tts.speech_synthesis_test.SpeechSynthesisTestDatasetBuilder(data_csv, config=None)

Bases: athena.data.datasets.base.BaseDatasetBuilder

SpeechSynthesisDatasetBuilder

property num_class

@property

Returns

the max_index of the vocabulary

Return type

int

property sample_type

@property

Returns

sample_type of the dataset:

{
    "utt_id": tf.string,
    "input": tf.int32,
    "input_length": tf.int32,
    "speaker": tf.int32,
}

Return type

dict

property sample_shape

@property

Returns

sample_shape of the dataset:

{
    "utt_id": tf.TensorShape([]),
    "input": tf.TensorShape([None]),
    "input_length": tf.TensorShape([]),
    "speaker": tf.TensorShape([]),
}

Return type

dict

property sample_signature

@property

Returns

sample_signature of the dataset:

{
    "utt_id": tf.TensorSpec(shape=(None), dtype=tf.string),
    "input": tf.TensorSpec(shape=(None, None), dtype=tf.int32),
    "input_length": tf.TensorSpec(shape=(None), dtype=tf.int32),
    "speaker": tf.TensorSpec(shape=(None), dtype=tf.int32)
}

Return type

dict

default_config

preprocess_data(file_path)

generate a list of tuples (utt_id, transcript).

__getitem__(index)

compute_cmvn_if_necessary(is_necessary=True)

compute cmvn file